agentmods.dev

legal-setup

legal-setup is a command for Claude Code from ARCASSystems/FounderOS. It costs 44 tokens per session (1,886 once invoked), scanned A, original, MIT.

A guided setup command for configuring legal and compliance information for a business jurisdiction, such as a country or special legal region.

In plain words
What is it for?
Use it when setting up the legal-compliance skill, after moving jurisdictions, or after changing the fiscal year or business structure.
Why use it?
It records the jurisdiction, fiscal-year details, and deadlines needed for later compliance work.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Claude Code.

Part of the founder-os plugin — 95 skills, 45 commands, 6 hooks shipped together

not rated 5 22d ago A scan 44 tokens original MIT
View the source file ARCASSystems/FounderOS
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/arcassystems/founderos/legal-setup
Clone the repo
git clone --depth 1 https://github.com/ARCASSystems/FounderOS

Made for: Claude Code.

Or install founder-os, the plugin that ships this one along with the rest of its 95 skills, 45 commands, 6 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for legal-setup

README.md
[![agentmods](https://agentmods.dev/badge/commands/arcassystems/founderos/legal-setup.svg)](https://agentmods.dev/commands/arcassystems/founderos/legal-setup)
Your own site
<a href="https://agentmods.dev/commands/arcassystems/founderos/legal-setup"><img src="https://agentmods.dev/badge/commands/arcassystems/founderos/legal-setup.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,886 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00044 $0.01886
Opus 5 $0.00022 $0.00943
Sonnet 5 $0.00009 $0.00377
Haiku 4.5 $0.00004 $0.00189

Measured 5d ago against content hash e08eaf070d4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

legal-setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/legal-setup.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Interactive wizard that wires the legal-compliance skill to your jurisdiction. Run once at install, or after a material change (fiscal year, jurisdiction, business structure).

This command is a thin trigger - the heavy lifting lives in skills/legal-compliance/SKILL.md.

Procedure

  1. Verify install. If core/identity.md does not exist, reply: Founder OS not set up here. Say "set up Founder OS" first. and stop.

  2. Read the legal-compliance skill at skills/legal-compliance/SKILL.md. If it is missing, reply: legal-compliance skill not found. Restarting Claude Code fixes this most of the time, because it reloads what is installed. If it happens again after a restart, say "update Founder OS". and stop.

  3. Run the interview. Ask ONE question at a time. Wait for the answer before moving on.

Q1 - Jurisdiction

Ask: "What jurisdiction does your business operate under? Examples: UAE, UAE-DIFC, UAE-ADGM, US-Delaware-LLC, UK-Ltd, IN-Karnataka-Pvt-Ltd, SG-Pte-Ltd, AU-Pty-Ltd. If you operate across multiple, name your primary one - we can add others later."

Map the answer to a folder slug (lowercase, dash-separated). Examples:

  • "UAE" or "Dubai mainland" → uae
  • "DIFC" → uae-difc
  • "Delaware LLC" → us-delaware-llc
  • "UK Ltd" → uk-ltd

Check whether skills/legal-compliance/references/<slug>/ already exists.

  • UAE / UAE-Dubai-Mainland / UAE-Abu-Dhabi-Mainland: maps to existing references/uae/ folder. Skill is ready to answer.
  • UAE-DIFC / UAE-ADGM: also uses references/uae/ (each domain file has DIFC/ADGM sections). Note in the response that DIFC/ADGM are separate common-law regimes and the skill flags them on every answer.
  • Anything else: the folder does NOT exist. Continue to Q2.

Q2 - (Non-UAE only) Confirm scaffold creation

If the jurisdiction folder does not exist:

Tell the user: "I don't have a reference set for <jurisdiction> yet. The skill ships with UAE as the worked example - your jurisdiction needs the same shape, populated with your country's gazetted sources. I'll create an empty scaffold under references/<slug>/. To start answering questions, you'll need to load at least three sources (tax authority, business law, labour law). Want to proceed? (yes / no)"

Read the full file on GitHub · 140 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 140 lines · 44 tokens per session scan A e08eaf070d4b

Subscribe to this mod's changes

legal-setup is a command published in the GitHub repository ARCASSystems/FounderOS (5 stars, last pushed 22d ago), licensed MIT. It adds 44 tokens to every session and 1,886 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Legal and complianceai-agentsclaude-codefounder-osllms-txtmarkdownoperating-system
Related

Other commands, from other repositories

gtm:compliance

Configure privacy and anti-spam regulation toggles for a workspace.

shyftai/GTMOS · 18 tokens

web:compliance

Configure content compliance and brand safety rules.

shyftai/WEBOS · 12 tokens

voice-compliance

Voice/telephony compliance check — invokes voice-ai-reviewer to produce TM-voice-{slug}.md with TCPA, STIR/SHAKEN, state recording-consent, EU AI Act Art. 50, and synth-voice deepfake-law gaps.

avelikiy/great_cto · 53 tokens

au-pspf

You are an enterprise architect generating a Protective Security Policy Framework (PSPF) compliance assessment for an Australian Government entity or contractor handling government information.

tractorjuice/arc-kit · 33 tokens

compliance-audit

Full regulatory compliance audit for GDPR, HIPAA, SOC2, PCI-DSS, ISO 27001, and other frameworks with gap analysis, remediation planning, and evidence collection.

TheLobbi/claude · 0 tokens

um-setup

First-run setup — point the plugin at your universal-memory server, verify it, save config.

goldenwo/universal-memory · 18 tokens